Improved Sea-Ice Identification Using Semantic Segmentation With Raindrop Removal
Sea-ice identification is an essential process for safety critical navigation support of surface vessels in polar waters. Semantic segmentation has drawn much attention as an enabling technique for fast detection of objects in a scene including sea-ice conditions. Identifying sea-ice is a challengin...
Published in: | IEEE Access |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2022
|
Subjects: | |
Online Access: | https://research.library.mun.ca/15545/ https://research.library.mun.ca/15545/1/Improved_Sea-Ice_Identification_Using_Semantic_Segmentation_With_Raindrop_Removal.pdf https://doi.org/10.1109/ACCESS.2022.3150969 |
id |
ftmemorialuniv:oai:research.library.mun.ca:15545 |
---|---|
record_format |
openpolar |
spelling |
ftmemorialuniv:oai:research.library.mun.ca:15545 2023-10-01T03:59:21+02:00 Improved Sea-Ice Identification Using Semantic Segmentation With Raindrop Removal Alsharay, Nahed M. Chen, Yuanzhu Dobre, Octavia A. De Silva, Oscar 2022-02-10 application/pdf https://research.library.mun.ca/15545/ https://research.library.mun.ca/15545/1/Improved_Sea-Ice_Identification_Using_Semantic_Segmentation_With_Raindrop_Removal.pdf https://doi.org/10.1109/ACCESS.2022.3150969 en eng Institute of Electrical and Electronics Engineers (IEEE) https://research.library.mun.ca/15545/1/Improved_Sea-Ice_Identification_Using_Semantic_Segmentation_With_Raindrop_Removal.pdf Alsharay, Nahed M. <https://research.library.mun.ca/view/creator_az/Alsharay=3ANahed_M=2E=3A=3A.html> and Chen, Yuanzhu <https://research.library.mun.ca/view/creator_az/Chen=3AYuanzhu=3A=3A.html> and Dobre, Octavia A. <https://research.library.mun.ca/view/creator_az/Dobre=3AOctavia_A=2E=3A=3A.html> and De Silva, Oscar <https://research.library.mun.ca/view/creator_az/De_Silva=3AOscar=3A=3A.html> (2022) Improved Sea-Ice Identification Using Semantic Segmentation With Raindrop Removal. IEEE Access, 10. ISSN 2169-3536 cc_by_nc Article PeerReviewed 2022 ftmemorialuniv https://doi.org/10.1109/ACCESS.2022.3150969 2023-09-03T06:50:18Z Sea-ice identification is an essential process for safety critical navigation support of surface vessels in polar waters. Semantic segmentation has drawn much attention as an enabling technique for fast detection of objects in a scene including sea-ice conditions. Identifying sea-ice is a challenging problem, especially in the presence of raindrops. The raindrop alters the boundaries of the objects in the scene, and thus, degrades the identification performance. In this work, a raindrop removing framework is developed to enhance the classification performance. Three deep-learning semantic segmentation networks are trained to classify the scene of sea-ice images into ice, water, ship, and sky. The deep-learning networks are VGG-16, fully convolutional network, and pyramid scene parsing network. Transfer learning along with data augmentation operations have been implemented to improve the training process. Results illustrate that data augmentation operations enhance the performance of the three models. Moreover, the raindrop removing framework improves the models’ performance, e.g. the average intersection over union of the VGG-16 model is improved from 85.91% to 91.70%. Article in Journal/Newspaper Sea ice Memorial University of Newfoundland: Research Repository Pyramid ENVELOPE(157.300,157.300,-81.333,-81.333) IEEE Access 10 21599 21607 |
institution |
Open Polar |
collection |
Memorial University of Newfoundland: Research Repository |
op_collection_id |
ftmemorialuniv |
language |
English |
description |
Sea-ice identification is an essential process for safety critical navigation support of surface vessels in polar waters. Semantic segmentation has drawn much attention as an enabling technique for fast detection of objects in a scene including sea-ice conditions. Identifying sea-ice is a challenging problem, especially in the presence of raindrops. The raindrop alters the boundaries of the objects in the scene, and thus, degrades the identification performance. In this work, a raindrop removing framework is developed to enhance the classification performance. Three deep-learning semantic segmentation networks are trained to classify the scene of sea-ice images into ice, water, ship, and sky. The deep-learning networks are VGG-16, fully convolutional network, and pyramid scene parsing network. Transfer learning along with data augmentation operations have been implemented to improve the training process. Results illustrate that data augmentation operations enhance the performance of the three models. Moreover, the raindrop removing framework improves the models’ performance, e.g. the average intersection over union of the VGG-16 model is improved from 85.91% to 91.70%. |
format |
Article in Journal/Newspaper |
author |
Alsharay, Nahed M. Chen, Yuanzhu Dobre, Octavia A. De Silva, Oscar |
spellingShingle |
Alsharay, Nahed M. Chen, Yuanzhu Dobre, Octavia A. De Silva, Oscar Improved Sea-Ice Identification Using Semantic Segmentation With Raindrop Removal |
author_facet |
Alsharay, Nahed M. Chen, Yuanzhu Dobre, Octavia A. De Silva, Oscar |
author_sort |
Alsharay, Nahed M. |
title |
Improved Sea-Ice Identification Using Semantic Segmentation With Raindrop Removal |
title_short |
Improved Sea-Ice Identification Using Semantic Segmentation With Raindrop Removal |
title_full |
Improved Sea-Ice Identification Using Semantic Segmentation With Raindrop Removal |
title_fullStr |
Improved Sea-Ice Identification Using Semantic Segmentation With Raindrop Removal |
title_full_unstemmed |
Improved Sea-Ice Identification Using Semantic Segmentation With Raindrop Removal |
title_sort |
improved sea-ice identification using semantic segmentation with raindrop removal |
publisher |
Institute of Electrical and Electronics Engineers (IEEE) |
publishDate |
2022 |
url |
https://research.library.mun.ca/15545/ https://research.library.mun.ca/15545/1/Improved_Sea-Ice_Identification_Using_Semantic_Segmentation_With_Raindrop_Removal.pdf https://doi.org/10.1109/ACCESS.2022.3150969 |
long_lat |
ENVELOPE(157.300,157.300,-81.333,-81.333) |
geographic |
Pyramid |
geographic_facet |
Pyramid |
genre |
Sea ice |
genre_facet |
Sea ice |
op_relation |
https://research.library.mun.ca/15545/1/Improved_Sea-Ice_Identification_Using_Semantic_Segmentation_With_Raindrop_Removal.pdf Alsharay, Nahed M. <https://research.library.mun.ca/view/creator_az/Alsharay=3ANahed_M=2E=3A=3A.html> and Chen, Yuanzhu <https://research.library.mun.ca/view/creator_az/Chen=3AYuanzhu=3A=3A.html> and Dobre, Octavia A. <https://research.library.mun.ca/view/creator_az/Dobre=3AOctavia_A=2E=3A=3A.html> and De Silva, Oscar <https://research.library.mun.ca/view/creator_az/De_Silva=3AOscar=3A=3A.html> (2022) Improved Sea-Ice Identification Using Semantic Segmentation With Raindrop Removal. IEEE Access, 10. ISSN 2169-3536 |
op_rights |
cc_by_nc |
op_doi |
https://doi.org/10.1109/ACCESS.2022.3150969 |
container_title |
IEEE Access |
container_volume |
10 |
container_start_page |
21599 |
op_container_end_page |
21607 |
_version_ |
1778533275067744256 |